Merge git://1984.lsi.us.es/nf-next

Pablo Neira Ayuso says:

====================
This is the first batch of Netfilter and IPVS updates for your
net-next tree. Mostly cleanups for the Netfilter side. They are:

* Remove unnecessary RTNL locking now that we have support
  for namespace in nf_conntrack, from Patrick McHardy.

* Cleanup to eliminate unnecessary goto in the initialization
  path of several Netfilter tables, from Jean Sacren.

* Another cleanup from Wu Fengguang, this time to PTR_RET instead
  of if IS_ERR then return PTR_ERR.

* Use list_for_each_entry_continue_rcu in nf_iterate, from
  Michael Wang.

* Add pmtu_disc sysctl option to disable PMTU in their tunneling
  transmitter, from Julian Anastasov.

* Generalize application protocol registration in IPVS and modify
  IPVS FTP helper to use it, from Julian Anastasov.

* update Kconfig. The IPVS FTP helper depends on the Netfilter FTP
  helper for NAT support, from Julian Anastasov.

* Add logic to update PMTU for IPIP packets in IPVS, again
  from Julian Anastasov.

* A couple of sparse warning fixes for IPVS and Netfilter from
  Claudiu Ghioc and Patrick McHardy respectively.

Patrick's IPv6 NAT changes will follow after this batch, I need
to flush this batch first before refreshing my tree.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 191 insertions, 66 deletions

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index f987138..8b2cffd 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -250,7 +250,8 @@ comment 'IPVS application helper'
 
 config	IP_VS_FTP
   	tristate "FTP protocol helper"
-        depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT
+	depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \
+		NF_CONNTRACK_FTP
 	select IP_VS_NFCT
 	---help---
 	  FTP is a protocol that transfers IP address and/or port number in
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 64f9e8f..9713e6e 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -180,22 +180,38 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
 }
 
 
-/*
- *	ip_vs_app registration routine
- */
-int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
+/* Register application for netns */
+struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
-	/* increase the module use count */
-	ip_vs_use_count_inc();
+	struct ip_vs_app *a;
+	int err = 0;
+
+	if (!ipvs)
+		return ERR_PTR(-ENOENT);
 
 	mutex_lock(&__ip_vs_app_mutex);
 
-	list_add(&app->a_list, &ipvs->app_list);
+	list_for_each_entry(a, &ipvs->app_list, a_list) {
+		if (!strcmp(app->name, a->name)) {
+			err = -EEXIST;
+			goto out_unlock;
+		}
+	}
+	a = kmemdup(app, sizeof(*app), GFP_KERNEL);
+	if (!a) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	INIT_LIST_HEAD(&a->incs_list);
+	list_add(&a->a_list, &ipvs->app_list);
+	/* increase the module use count */
+	ip_vs_use_count_inc();
 
+out_unlock:
 	mutex_unlock(&__ip_vs_app_mutex);
 
-	return 0;
+	return err ? ERR_PTR(err) : a;
 }
 
 
@@ -205,20 +221,29 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
  */
 void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
 {
-	struct ip_vs_app *inc, *nxt;
+	struct netns_ipvs *ipvs = net_ipvs(net);
+	struct ip_vs_app *a, *anxt, *inc, *nxt;
+
+	if (!ipvs)
+		return;
 
 	mutex_lock(&__ip_vs_app_mutex);
 
-	list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
-		ip_vs_app_inc_release(net, inc);
-	}
+	list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) {
+		if (app && strcmp(app->name, a->name))
+			continue;
+		list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) {
+			ip_vs_app_inc_release(net, inc);
+		}
 
-	list_del(&app->a_list);
+		list_del(&a->a_list);
+		kfree(a);
 
-	mutex_unlock(&__ip_vs_app_mutex);
+		/* decrease the module use count */
+		ip_vs_use_count_dec();
+	}
 
-	/* decrease the module use count */
-	ip_vs_use_count_dec();
+	mutex_unlock(&__ip_vs_app_mutex);
 }
 
 
@@ -586,5 +611,6 @@ int __net_init ip_vs_app_net_init(struct net *net)
 
 void __net_exit ip_vs_app_net_cleanup(struct net *net)
 {
+	unregister_ip_vs_app(net, NULL /* all */);
 	proc_net_remove(net, "ip_vs_app");
 }
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b54ecce..58918e2 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1303,7 +1303,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	struct ip_vs_conn *cp;
 	struct ip_vs_protocol *pp;
 	struct ip_vs_proto_data *pd;
-	unsigned int offset, ihl, verdict;
+	unsigned int offset, offset2, ihl, verdict;
+	bool ipip;
 
 	*related = 1;
 
@@ -1345,6 +1346,21 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	net = skb_net(skb);
 
+	/* Special case for errors for IPIP packets */
+	ipip = false;
+	if (cih->protocol == IPPROTO_IPIP) {
+		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
+			return NF_ACCEPT;
+		/* Error for our IPIP must arrive at LOCAL_IN */
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+			return NF_ACCEPT;
+		offset += cih->ihl * 4;
+		cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
+		if (cih == NULL)
+			return NF_ACCEPT; /* The packet looks wrong, ignore */
+		ipip = true;
+	}
+
 	pd = ip_vs_proto_data_get(net, cih->protocol);
 	if (!pd)
 		return NF_ACCEPT;
@@ -1358,11 +1374,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
 		      "Checking incoming ICMP for");
 
+	offset2 = offset;
 	offset += cih->ihl * 4;
 
 	ip_vs_fill_iphdr(AF_INET, cih, &ciph);
-	/* The embedded headers contain source and dest in reverse order */
-	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
+	/* The embedded headers contain source and dest in reverse order.
+	 * For IPIP this is error for request, not for reply.
+	 */
+	cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1);
 	if (!cp)
 		return NF_ACCEPT;
 
@@ -1376,6 +1395,57 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		goto out;
 	}
 
+	if (ipip) {
+		__be32 info = ic->un.gateway;
+
+		/* Update the MTU */
+		if (ic->type == ICMP_DEST_UNREACH &&
+		    ic->code == ICMP_FRAG_NEEDED) {
+			struct ip_vs_dest *dest = cp->dest;
+			u32 mtu = ntohs(ic->un.frag.mtu);
+
+			/* Strip outer IP and ICMP, go to IPIP header */
+			__skb_pull(skb, ihl + sizeof(_icmph));
+			offset2 -= ihl + sizeof(_icmph);
+			skb_reset_network_header(skb);
+			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
+				&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
+			rcu_read_lock();
+			ipv4_update_pmtu(skb, dev_net(skb->dev),
+					 mtu, 0, 0, 0, 0);
+			rcu_read_unlock();
+			/* Client uses PMTUD? */
+			if (!(cih->frag_off & htons(IP_DF)))
+				goto ignore_ipip;
+			/* Prefer the resulting PMTU */
+			if (dest) {
+				spin_lock(&dest->dst_lock);
+				if (dest->dst_cache)
+					mtu = dst_mtu(dest->dst_cache);
+				spin_unlock(&dest->dst_lock);
+			}
+			if (mtu > 68 + sizeof(struct iphdr))
+				mtu -= sizeof(struct iphdr);
+			info = htonl(mtu);
+		}
+		/* Strip outer IP, ICMP and IPIP, go to IP header of
+		 * original request.
+		 */
+		__skb_pull(skb, offset2);
+		skb_reset_network_header(skb);
+		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
+			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
+			ic->type, ic->code, ntohl(info));
+		icmp_send(skb, ic->type, ic->code, info);
+		/* ICMP can be shorter but anyways, account it */
+		ip_vs_out_stats(cp, skb);
+
+ignore_ipip:
+		consume_skb(skb);
+		verdict = NF_STOLEN;
+		goto out;
+	}
+
 	/* do the statistics and put it back */
 	ip_vs_in_stats(cp, skb);
 	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 72bf32a..3c60137 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1801,6 +1801,12 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "pmtu_disc",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #ifdef CONFIG_IP_VS_DEBUG
 	{
 		.procname	= "debug_level",
@@ -3676,7 +3682,7 @@ static void ip_vs_genl_unregister(void)
  * per netns intit/exit func.
  */
 #ifdef CONFIG_SYSCTL
-int __net_init ip_vs_control_net_init_sysctl(struct net *net)
+static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 {
 	int idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3727,6 +3733,8 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3);
 	tbl[idx++].data = &ipvs->sysctl_sync_retries;
 	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
+	ipvs->sysctl_pmtu_disc = 1;
+	tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
 
 
 	ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
@@ -3744,7 +3752,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	return 0;
 }
 
-void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
+static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
@@ -3755,8 +3763,8 @@ void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 
 #else
 
-int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
-void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
+static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
+static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
 
 #endif
 
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b20b29c..ad70b7e 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -441,16 +441,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 
 	if (!ipvs)
 		return -ENOENT;
-	app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL);
-	if (!app)
-		return -ENOMEM;
-	INIT_LIST_HEAD(&app->a_list);
-	INIT_LIST_HEAD(&app->incs_list);
-	ipvs->ftp_app = app;
 
-	ret = register_ip_vs_app(net, app);
-	if (ret)
-		goto err_exit;
+	app = register_ip_vs_app(net, &ip_vs_ftp);
+	if (IS_ERR(app))
+		return PTR_ERR(app);
 
 	for (i = 0; i < ports_count; i++) {
 		if (!ports[i])
@@ -464,9 +458,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 	return 0;
 
 err_unreg:
-	unregister_ip_vs_app(net, app);
-err_exit:
-	kfree(ipvs->ftp_app);
+	unregister_ip_vs_app(net, &ip_vs_ftp);
 	return ret;
 }
 /*
@@ -474,10 +466,7 @@ err_exit:
  */
 static void __ip_vs_ftp_exit(struct net *net)
 {
-	struct netns_ipvs *ipvs = net_ipvs(net);
-
-	unregister_ip_vs_app(net, ipvs->ftp_app);
-	kfree(ipvs->ftp_app);
+	unregister_ip_vs_app(net, &ip_vs_ftp);
 }
 
 static struct pernet_operations ip_vs_ftp_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 65b616a..543a554 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -49,6 +49,7 @@ enum {
 	IP_VS_RT_MODE_RDR	= 4, /* Allow redirect from remote daddr to
 				      * local
 				      */
+	IP_VS_RT_MODE_CONNECT	= 8, /* Always bind route to saddr */
 };
 
 /*
@@ -84,6 +85,42 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
 	return dst;
 }
 
+/* Get route to daddr, update *saddr, optionally bind route to saddr */
+static struct rtable *do_output_route4(struct net *net, __be32 daddr,
+				       u32 rtos, int rt_mode, __be32 *saddr)
+{
+	struct flowi4 fl4;
+	struct rtable *rt;
+	int loop = 0;
+
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.daddr = daddr;
+	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
+	fl4.flowi4_tos = rtos;
+
+retry:
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt)) {
+		/* Invalid saddr ? */
+		if (PTR_ERR(rt) == -EINVAL && *saddr &&
+		    rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
+			*saddr = 0;
+			flowi4_update_output(&fl4, 0, rtos, daddr, 0);
+			goto retry;
+		}
+		IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
+		return NULL;
+	} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+		ip_rt_put(rt);
+		*saddr = fl4.saddr;
+		flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr);
+		loop++;
+		goto retry;
+	}
+	*saddr = fl4.saddr;
+	return rt;
+}
+
 /* Get route to destination or remote server */
 static struct rtable *
 __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
@@ -98,20 +135,13 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		spin_lock(&dest->dst_lock);
 		if (!(rt = (struct rtable *)
 		      __ip_vs_dst_check(dest, rtos))) {
-			struct flowi4 fl4;
-
-			memset(&fl4, 0, sizeof(fl4));
-			fl4.daddr = dest->addr.ip;
-			fl4.flowi4_tos = rtos;
-			rt = ip_route_output_key(net, &fl4);
-			if (IS_ERR(rt)) {
+			rt = do_output_route4(net, dest->addr.ip, rtos,
+					      rt_mode, &dest->dst_saddr.ip);
+			if (!rt) {
 				spin_unlock(&dest->dst_lock);
-				IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
-					     &dest->addr.ip);
 				return NULL;
 			}
 			__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
-			dest->dst_saddr.ip = fl4.saddr;
 			IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
 				  "rtos=%X\n",
 				  &dest->addr.ip, &dest->dst_saddr.ip,
@@ -122,19 +152,17 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 			*ret_saddr = dest->dst_saddr.ip;
 		spin_unlock(&dest->dst_lock);
 	} else {
-		struct flowi4 fl4;
+		__be32 saddr = htonl(INADDR_ANY);
 
-		memset(&fl4, 0, sizeof(fl4));
-		fl4.daddr = daddr;
-		fl4.flowi4_tos = rtos;
-		rt = ip_route_output_key(net, &fl4);
-		if (IS_ERR(rt)) {
-			IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
-				     &daddr);
+		/* For such unconfigured boxes avoid many route lookups
+		 * for performance reasons because we do not remember saddr
+		 */
+		rt_mode &= ~IP_VS_RT_MODE_CONNECT;
+		rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
+		if (!rt)
 			return NULL;
-		}
 		if (ret_saddr)
-			*ret_saddr = fl4.saddr;
+			*ret_saddr = saddr;
 	}
 
 	local = rt->rt_flags & RTCF_LOCAL;
@@ -331,6 +359,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
 	old_dst = dest->dst_cache;
 	dest->dst_cache = NULL;
 	dst_release(old_dst);
+	dest->dst_saddr.ip = 0;
 }
 
 #define IP_VS_XMIT_TUNNEL(skb, cp)				\
@@ -766,12 +795,13 @@ int
 ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp)
 {
+	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
 	struct rtable *rt;			/* Route to the other host */
 	__be32 saddr;				/* Source for tunnel */
 	struct net_device *tdev;		/* Device to other host */
 	struct iphdr  *old_iph = ip_hdr(skb);
 	u8     tos = old_iph->tos;
-	__be16 df = old_iph->frag_off;
+	__be16 df;
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	int    mtu;
@@ -781,7 +811,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
 				      RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
-						   IP_VS_RT_MODE_NON_LOCAL,
+						   IP_VS_RT_MODE_NON_LOCAL |
+						   IP_VS_RT_MODE_CONNECT,
 						   &saddr)))
 		goto tx_error_icmp;
 	if (rt->rt_flags & RTCF_LOCAL) {
@@ -796,13 +827,13 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
 		goto tx_error_put;
 	}
-	if (skb_dst(skb))
+	if (rt_is_output_route(skb_rtable(skb)))
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
-	df |= (old_iph->frag_off & htons(IP_DF));
+	/* Copy DF, reset fragment offset and MF */
+	df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
 
-	if ((old_iph->frag_off & htons(IP_DF) &&
-	    mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
+	if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) {
 		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
 		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
 		goto tx_error_put;